Incremental Pedestrian Attribute Recognition via Dual Uncertainty-Aware Pseudo-Labeling

doi:10.1109/TIFS.2023.3268887

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Incremental Pedestrian Attribute Recognition via Dual Uncertainty-Aware Pseudo-Labeling
	Li, Da 3; Zhang, Zhang 1,2; Shan, Caifeng 4,5; Wang, Liang 1,2
刊名	IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
	2023
卷号	18 页码:2622-2636
关键词	Uncertainty Task analysis Training Visualization Benchmark testing Measurement uncertainty Estimation Pedestrian attribute recognition continual learning uncertainty estimation
ISSN号	1556-6013
DOI	10.1109/TIFS.2023.3268887
通讯作者	Zhang, Zhang(zzhang@nlpr.ia.ac.cn)
英文摘要	Incremental pedestrian attribute recognition (IncPAR) aims to learn novel person attributes continuously and avoid the catastrophic forgetting, which is an essential problem for image forensic and security applications, e.g., suspect search. Different from the conventional continual learning for visual classification, we formulate the IncPAR as a problem of multi-label continual learning with incomplete labels (MCL-IL), where the training samples in a novel task are annotated with only a few categories of interest but may implicitly contain other attributes of previous tasks. The incomplete label assignments is a challenging and frequently-encountered issue in real-world multi-label classification applications due to a number of reasons, e.g., incomplete data collection, moderate budget for annotations, etc. To tackle the MCL-IL problem, we propose a self-training based approach via dual uncertainty-aware pseudo-labeling (DUAPL) to transfer the knowledge learned in previous tasks to novel tasks. Specially, both kinds of uncertainties, i.e., aleatoric uncertainty and epistemic uncertainty, are modeled to mitigate the negative influences of noisy pseudo labels induced by low quality samples and immature models learned by inadequate training in early tasks. Based on the DUAPL, more reliable supervision signals can be estimated to prevent the model evolution from forgetting attributes seen in previous tasks. For standard evaluations of MCL-IL methods, two benchmarks on IncPAR, termed RAP-CL and PETA-CL, are constructed by re-organizing public human attribute datasets. Extensive experiments have been performed on these benchmarks to compare the proposed method with multiple baselines. The superior performance in terms of both recognition accuracies and forgetting ratios demonstrate the effectiveness of the proposed DUAPL for IncPAR.
资助项目	National Key Research and Development Program of China[2022ZD0117901] ; National Natural Science Foundation of China[62236010] ; National Natural Science Foundation of China[62076078] ; National Natural Science Foundation of China[61972188] ; Talent Introduction Program for Youth Innovation Teams of Shandong Province
WOS关键词	MODEL
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000981885300002
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Talent Introduction Program for Youth Innovation Teams of Shandong Province
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53329]
专题	多模态人工智能系统全国重点实验室
通讯作者	Zhang, Zhang
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Beijing 100190, Peoples R China 4.Shandong Univ Sci & Technol, Coll Elect Engn & Automat, Qingdao 266590, Peoples R China 5.Nanjing Univ, Natl Key Lab Novel Software Technol, Nanjing 210023, Peoples R China
推荐引用方式 GB/T 7714	Li, Da,Zhang, Zhang,Shan, Caifeng,et al. Incremental Pedestrian Attribute Recognition via Dual Uncertainty-Aware Pseudo-Labeling[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2023,18:2622-2636.
APA	Li, Da,Zhang, Zhang,Shan, Caifeng,&Wang, Liang.(2023).Incremental Pedestrian Attribute Recognition via Dual Uncertainty-Aware Pseudo-Labeling.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,18,2622-2636.
MLA	Li, Da,et al."Incremental Pedestrian Attribute Recognition via Dual Uncertainty-Aware Pseudo-Labeling".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 18(2023):2622-2636.